Chest X-Ray Pneumonia Classification using Deep Learning
This project uses the Chest X-Ray Pneumonia dataset from Kaggle, which contains labeled chest radiograph images classified as Normal or Pneumonia. The dataset is designed for supervised image classification tasks and is widely used for developing and benchmarking deep learning models in medical image analysis.
Mentor Details:
Orna Bregman Amitai
Mentor Details:
Requirments:
- Build a deep learning model to classify chest X-ray images as Normal or Pneumonia.
- Apply data preprocessing and augmentation to improve model robustness.
- Train and evaluate convolutional neural networks using standard performance metrics.
- Analyze model errors and generalization behavior.
Problem Statement
Pneumonia is a serious respiratory infection and a major cause of mortality worldwide. Interpreting chest X-ray images requires expert radiologists and is subject to variability. Automated deep learning-based classification systems can assist clinicians by improving diagnostic speed, consistency, and accessibility, especially in resource-limited settings.
Project Objectives
- Build a deep learning model to classify chest X-ray images as Normal or Pneumonia.
- Apply data preprocessing and augmentation to improve model robustness.
- Train and evaluate convolutional neural networks using standard performance metrics.
- Analyze model errors and generalization behavior.
Technical Scope
- Image preprocessing (resizing, normalization)
- Data augmentation for medical images
- Training convolutional neural networks (CNNs)
- Model evaluation using accuracy, precision, recall, and confusion matrices
- Optional use of transfer learning with pre-trained models
Required Knowledge and Prerequisites
Core Requirements:
- Python programming
- Machine learning and deep learning fundamentals
- Experience with TensorFlow or PyTorch
Recommended Background:
- Computer vision fundamentals
- Understanding of CNN architectures
- Familiarity with medical imaging data
Project Difficulty and Expected Level
Overall Difficulty: Beginners
This project is well-suited for:
Teams of 1–3 students
Expected Outcomes
- A trained CNN model for pneumonia detection from chest X-rays
- Quantitative evaluation results on validation and test sets
- A reproducible training and inference pipeline
- Practical experience applying AI to medical imaging problems